軌跡一致性蒸餾

摘要

潛在一致性模型（LCM）將一致性模型擴展至潛在空間，並利用引導一致性蒸餾技術，在加速文本到圖像合成方面取得了令人印象深刻的表現。然而，我們觀察到LCM 在生成既清晰又詳細複雜的圖像方面存在困難。為了解決這一限制，我們首先深入探討並闡明潛在原因。我們的研究識別出主要問題來自三個不同領域的錯誤。因此，我們引入了軌跡一致性蒸餾（TCD），其中包括軌跡一致性函數和策略性隨機抽樣。軌跡一致性函數通過擴大自一致性邊界條件的範圍，賦予TCD 準確追踪概率流ODE 整個軌跡的能力，從而減少蒸餾錯誤。此外，策略性隨機抽樣專門設計用於規避多步一致性抽樣中積累的錯誤，精心設計以補充TCD 模型。實驗表明，TCD 不僅在低NFEs 下顯著提高圖像質量，而且在高NFEs 下與教師模型相比產生更詳細的結果。

English

Latent Consistency Model (LCM) extends the Consistency Model to the latent space and leverages the guided consistency distillation technique to achieve impressive performance in accelerating text-to-image synthesis. However, we observed that LCM struggles to generate images with both clarity and detailed intricacy. To address this limitation, we initially delve into and elucidate the underlying causes. Our investigation identifies that the primary issue stems from errors in three distinct areas. Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling. The trajectory consistency function diminishes the distillation errors by broadening the scope of the self-consistency boundary condition and endowing the TCD with the ability to accurately trace the entire trajectory of the Probability Flow ODE. Additionally, strategic stochastic sampling is specifically designed to circumvent the accumulated errors inherent in multi-step consistency sampling, which is meticulously tailored to complement the TCD model. Experiments demonstrate that TCD not only significantly enhances image quality at low NFEs but also yields more detailed results compared to the teacher model at high NFEs.